Skip to content
Project categories

Machine Learning · GitHub

Train, evaluate, and run machine learning models.

Useful GitHub projects

12,805 projects
675stars

Features selector based on the self selected-algorithm, loss function and validation method

  • 6th in JData-2018
  • 12nd in IJCAI-2018 1st round

PZAD

Dyakonov

350stars

Курс "Прикладные задачи анализа данных" (ВМК, МГУ имени М.В. Ломоносова)

databook_matlab

dynamicslab

335stars

Matlab files with demo code intended as a companion to the book "Data-Driven Science and Engineering: Machine Learning, Dynamical Systems, and Control" by Steven L. Brunton and J. Nathan Kutz http://www.databookuw.com/

backdoors101

ebagdasa

387stars

Backdoors Framework for Deep Learning and Federated Learning. A light-weight tool to conduct your research on backdoors.

1,343stars
budgetml preview

Deploy a ML inference service on a budget in less than 10 lines of code.

  • Automatic FastAPI server endpoint generation (it's faster than Flask).
  • Fully interactive docs via Swagger.
Machine LearningPythonApache-2.0GitHub

inception

eclipse-inception

733stars
inception preview

INCEpTION provides a semantic annotation platform offering intelligent annotation assistance and knowledge management.

337stars

i. A practical application of Transformer (ViT) on 2-D physiological signal (EEG) classification tasks. Also could be tried with EMG, EOG, ECG, etc. ii. Including the attention of spatial dimension (channel attention) and *temporal dimension*. iii. Common spatial pattern (CSP), an efficient feature enhancement method, realized with Python.

MoE-Infinity

EfficientMoE

384stars

PyTorch library for cost-effective, fast and easy serving of MoE models.

  • Cost-effective. Expert offloading to host memory and SSD lets memory-constrained GPUs serve MoE models that would otherwise not fit. DeepSeek-V4-Flash additionally offloads FP4-quantized experts.
  • Fast. Activation-aware expert caching, prefetching, tracing, fused CUDA kernels, CUDA graph capture, Marlin INT4 GEMM, and FP4/MXFP4 expert paths keep the hot path lean.
Machine LearningPythonApache-2.0GitHub

eland

elastic

693stars

Python Client and Toolkit for DataFrames, Big Data, Machine Learning and ETL in Elasticsearch

Machine LearningPythonApache-2.0GitHub